Neural Information Squeezer for Causal Emergence
This addresses the challenge of detecting causal emergence in Markovian dynamical systems for researchers in causality and complex systems, representing a novel methodological advancement.
The paper tackles the problem of identifying emergent causality from time series data by proposing a machine learning framework called Neural Information Squeezer, which automatically extracts coarse-graining strategies and macro-state dynamics, demonstrating its effectiveness on several example systems.
The classic studies of causal emergence have revealed that in some Markovian dynamical systems, far stronger causal connections can be found on the higher-level descriptions than the lower-level of the same systems if we coarse-grain the system states in an appropriate way. However, identifying this emergent causality from the data is still a hard problem that has not been solved because the correct coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-state dynamics, as well as identify causal emergence directly from the time series data. By decomposing a coarse-graining operation into two processes: information conversion and information dropping out, we can not only exactly control the width of the information channel, but also can derive some important properties analytically including the exact expression of the effective information of a macro-dynamics. We also show how our framework can extract the dynamics on different levels and identify causal emergence from the data on several exampled systems.